Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2507 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.9244. Min Act: -0.1700
Data Index: 1375113 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.7056. Min Act: -0.1700
Data Index: 3932902 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.6744. Min Act: -0.1700
Data Index: 1123097 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.5806. Min Act: -0.1700
Data Index: 7026763 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.5494. Min Act: -0.1700
Data Index: 5071482 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.5181. Min Act: -0.1700
Data Index: 3934601 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.4556. Min Act: -0.1700
Data Index: 8327647 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.4244. Min Act: -0.1700
Data Index: 6233718 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3931. Min Act: -0.1700
Data Index: 5945842 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3931. Min Act: -0.1700
Data Index: 2460884 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3619. Min Act: -0.1700
Data Index: 6540690 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3306. Min Act: -0.1700
Data Index: 5157912 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3306. Min Act: -0.1700
Data Index: 5572736 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.3306. Min Act: -0.1700
Data Index: 8753335 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2994. Min Act: -0.1700
Data Index: 2281511 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2994. Min Act: -0.1700
Data Index: 4661679 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2994. Min Act: -0.1700
Data Index: 6435623 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2681. Min Act: -0.1700
Data Index: 5402571 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2369. Min Act: -0.1700
Data Index: 4352129 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9244. Min Range: -6.9244
Max Act: 6.2681. Min Act: -0.1700
Data Index: 5656453 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19